Search

Wildlife roadkill is a recurring, dangerous problem that affects both humans and animals and has received increasing attention from environmentalists worldwide. Addressing this problem is difficult due to the high investments required in road infrastructure to effectively reduce wildlife vehicle collisions. Despite recent applications of machine learning techniques in low-cost and economically viable detection systems, e.g., for alerting drivers about the presence of animals and collecting statistics on endangered animal species, the success and wide adoption of these systems depend heavily on the availability of data for system training. The lack of training data negatively impacts the feature extraction of machine learning models, which is crucial for successful animal detection and classification. In this paper, we evaluate the performance of several state-of-the-art object detection models on limited data for model training. The selected models are based on the YOLO architecture, which is well-suited for and commonly used in real-time object detection. These include the YoloV4, Scaled-YoloV4, YoloV5, YoloR, YoloX, and YoloV7 models. We focus on Brazilian endangered animal species and use the BRA-Dataset for model training. We also assess the effectiveness of data augmentation and transfer learning techniques in our evaluation. The models are compared using summary metrics such as precision, recall, mAP, and FPS and are qualitatively analyzed considering classic computer vision problems. The results show that the architecture with the best results against false negatives is Scaled-YoloV4, while the best FPS detection score is the nano version of YoloV5., (© 2024. The Author(s).)

Cross-habitat spillover may be the outcome of a process of habitat loss or degradation where the receiving habitat serves as a refuge for organisms. Once surface habitats are lost or degraded, animals can find underground refuge in caves. This paper is focused on testing whether taxonomic order richness inside caves is positively affected by the loss of the native vegetation cover surrounding caves; whether degradation of native vegetation cover predicts cave community composition; and whether there is a pattern of cave community clusters delimited by similarity in the effects of habitat degradation on animal communities. We gathered a comprehensive speleological dataset consisting of occurrence data of thousands of invertebrates and vertebrates sampled in 864 iron caves in the Amazon, to test the effects of both variables measured inside caves and surrounding landscapes on spatial variation in richness and composition of animal communities. We show that caves can work as refuges for the fauna in landscapes where the native vegetation cover surrounding them was degraded, which was evidenced by landcover change increasing the richness of cave communities and clustering caves by similarity in community composition. Therefore, habitat degradation on the surface should be a key variable when characterizing cave ecosystems for conservation prioritization and offset planning. Habitat degradation causing a cross-habitat spillover effect highlights the importance of maintaining the connection between caves by the surface, especially large caves. Our study can help guide industry and stakeholders working on the complex conciliation between land use and biodiversity conservation., (© 2023. The Author(s).)